Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2953 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.0746. Min Range: -4.0746

Max Act: 4.0746. Min Act: -0.1700

Data Index: 1209541 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.8213. Min Act: -0.1700

Data Index: 181422 (Open Web Text)

Max Activating Token Index: 324

Text #2

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.7452. Min Act: -0.1700

Data Index: 3059471 (Open Web Text)

Max Activating Token Index: 136

Text #3

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.7112. Min Act: -0.1700

Data Index: 3762163 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.7521. Min Act: -0.1700

Data Index: 181447 (Open Web Text)

Max Activating Token Index: 573

Text #5

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.7183. Min Act: -0.1700

Data Index: 3588960 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.6662. Min Act: -0.1700

Data Index: 4240295 (Open Web Text)

Max Activating Token Index: 27

Text #7

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.6409. Min Act: -0.1700

Data Index: 181405 (Open Web Text)

Max Activating Token Index: 94

Text #8

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.6086. Min Act: -0.1700

Data Index: 181403 (Open Web Text)

Max Activating Token Index: 754

Text #9

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.6520. Min Act: -0.1700

Data Index: 181440 (Open Web Text)

Max Activating Token Index: 181

Text #10

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.5944. Min Act: -0.1700

Data Index: 6337404 (Open Web Text)

Max Activating Token Index: 121

Text #11

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.5931. Min Act: -0.1700

Data Index: 80038 (Open Web Text)

Max Activating Token Index: 324

Text #12

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.6127. Min Act: -0.1700

Data Index: 5203047 (Open Web Text)

Max Activating Token Index: 14

Text #13

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.6023. Min Act: -0.1700

Data Index: 3912386 (Open Web Text)

Max Activating Token Index: 433

Text #14

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.5964. Min Act: -0.1700

Data Index: 181404 (Open Web Text)

Max Activating Token Index: 368

Text #15

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.5497. Min Act: -0.1700

Data Index: 2068338 (Open Web Text)

Max Activating Token Index: 587

Text #16

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.5834. Min Act: -0.1700

Data Index: 181425 (Open Web Text)

Max Activating Token Index: 848

Text #17

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.5550. Min Act: -0.1700

Data Index: 2511719 (Open Web Text)

Max Activating Token Index: 86

Text #18

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.5587. Min Act: -0.1700

Data Index: 2645690 (Open Web Text)

Max Activating Token Index: 80

Text #19

Max Range: 4.0746. Min Range: -4.0746

Max Act: 3.5523. Min Act: -0.1700

Data Index: 181446 (Open Web Text)

Max Activating Token Index: 715